From 2b964134b42617ff34448aaa03b0335481a1af1a Mon Sep 17 00:00:00 2001 From: Alexey Date: Fri, 15 Jun 2018 17:43:00 +0300 Subject: [PATCH] Update Readme.md --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index db0f9459..b40d531d 100644 --- a/README.md +++ b/README.md @@ -320,6 +320,8 @@ It will create `.txt`-file for each `.jpg`-image-file - in the same directory an **Note:** If during training you see `nan` values for `avg` (loss) field - then training goes wrong, but if `nan` is in some other lines - then training goes well. + **Note:** If you changed width= or height= in your cfg-file, then new width and height must be divisible by 32. + ### How to train tiny-yolo (to detect your custom objects): Do all the same steps as for the full yolo model as described above. With the exception of: